A
licenseA
qualityA
maintenanceEnables verification of AI coding agent self-reports against git diff truth and a deterministic gate, producing pass/regenerate/reject directives to ensure claimed work matches actual changes.
6
AGPL 3.0
weekly-verify
Related Servers
Alternatives to weekly-verify
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityAmaintenanceDeterministic verification for AI-generated analysis. Reconciliation, consistency and Excel-integrity checks that stop the line when the numbers don't add up.45 PyPI1MIT
- FlicenseNot gradedqualityCmaintenanceThis MCP server verifies that an agent’s claimed tool output matches the actual response returned by a tool to prevent invented or distorted results. It flags mismatches, omissions, and invented fields to ensure downstream logic only processes verified tool data.-
- FlicenseNot gradedqualityBmaintenanceEnables construction management supervision automation by parsing submitted documents and cross-verifying numerical values against real-time Korean national laws and KCSC construction standards, then generating CM review draft reports.-
- AlicenseAqualityBmaintenanceCompare design and implementation screenshots using pixel-by-pixel analysis, generating visual diff images and metrics.111 npmMIT
EVIDIQ Rubric MCPofficial
AlicenseNot gradedqualityBmaintenanceDetermines whether a deliverable meets its contract using deterministic rules, criteria, and signed attestations.1MIT
TDQS
A4.6/5.0
Scored across 10 tools
Disambiguation5/5
Each tool owns a distinct stage or verification level (L1/L2 vs L3 vs L4), and the descriptions explicitly cross-reference when another tool should be used instead. The aggregate preview tool is clearly positioned as a convenience wrapper over the intermediate tools, so there is no real ambiguity.
Naming Consistency5/5
All tool names follow a consistent snake_case verb_noun pattern with specific, informative verbs: list, read, compute, extract, verify, check, flag, preview, save. The naming style is uniform and each name accurately predicts the tool's operation.
Tool Count5/5
Ten tools map cleanly onto the stages of the verification pipeline: discover targets, load source, compute expected findings, parse report, extract claims, verify values, check completeness, flag narrative risks, preview, and save. The count is well-scoped and every tool has a clear purpose.
Completeness5/5
The set covers the full verification lifecycle from target discovery through source normalization, report parsing, claim extraction, multi-level checks, all-level preview, and an approval-gated save. There are no obvious dead ends: the only write tool is intentionally gated, and every intermediate tool feeds into the preview/save flow.
Maintenance
ActivityMaintained
ResponsivenessNo issues